INDEX

Explanations

recipes including specific measurements and ingredients

oai_token-act-pair · gpt-3.5-turbo

quantities and measurements for ingredients in recipes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liga

-0.66

ulla

-0.63

raltar

-0.61

RAW

-0.60

 abiding

-0.59

OTOS

-0.59

ends

-0.58

ÅĤ

-0.57

Joy

-0.57

çĭ

-0.57

POSITIVE LOGITS

 Mask

0.65

 inhibition

0.63

involved

0.62

rance

0.61

 spoil

0.59

 teaspoon

0.59

cule

0.58

hedral

0.58

 metab

0.57

 equation

0.56

Activations Density 0.062%

recipes including specific measurements and ingredients

quantities and measurements for ingredients in recipes

No Comments

No Known Activations